INDEX

Explanations

references to sensitive information or data

oai_token-act-pair · gpt-3.5-turbo

references to sensitive data or information

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FIN

-0.85

AUT

-0.77

UNCH

-0.76

LOAD

-0.73

aneers

-0.71

ulhu

-0.70

SN

-0.69

 Wolver

-0.68

BO

-0.67

swick

-0.67

POSITIVE LOGITS

 sensitive

1.06

ivities

1.00

mble

0.98

ly

0.79

 sensit

0.79

ively

0.76

itiz

0.76

itized

0.74

itives

0.74

 sensitivity

0.74

Activations Density 0.015%

references to sensitive information or data

references to sensitive data or information

No Comments

No Known Activations